mnema

Official

Overview Schema Source Related Servers Discussions Admin

Move a decision through the workflow

decision_transition

Move a decision to a new state: accept, reject, or supersede it with a successor. Records the verdict and its reason in the append-only decision log.

Instructions

Move an existing decision to a new state. accept and reject a proposed decision (each needs a note); supersede a proposed or accepted decision with a later one: supersede needs the successor decision id in by and a reason. by applies ONLY to supersede; accept and reject REFUSE it. An illegal move or missing proof is refused with the gate’s reason. The decision is looked for in EVERY project of this workspace and the move lands in the project that holds it: the id decides, so no project is taken. An acceptance made through this tool is recorded as an agent’s, says so in the reply, and is marked as such wherever the decision is read. The switch agent-accepts turns it off, and then an accept is refused. RECORDING IS PERMANENT: mnema is append-only and nothing deletes a fact. A record in the public scope is committed to the repository and reaches every machine that clones it (published, if that repository is public). So do NOT record credentials here. Values in a recognized format (cloud keys, API tokens, private keys, a password inside a URL) are replaced with a typed placeholder before anything is written and the reply says what was replaced, but a format mnema does not recognize is written verbatim and cannot be taken back. Do not record personal data either: an email address is replaced with and reported, and the mnid already says who wrote. Each text field holds at most 65536 bytes; a longer one is refused, not truncated.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>",
      "action": "<action>"
    },
    "name": "decision_transition"
  }
}

Input Schema

Name	Required	Description
`by`	No	The successor decision id: required by supersede, refused with any other action.
`id`	Yes	The decision id to move.
`note`	No	Why this verdict (accept, reject).
`action`	Yes	The transition: accept, reject, or supersede.
`reason`	No	Why it is being replaced (supersede).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing that recording is permanent and append-only, that public-scope records are committed to the repository and reach every clone, that credentials are replaced with typed placeholders while unrecognized formats are stored verbatim, that emails are masked, that text fields cap at 65536 bytes and are refused rather than truncated, and that illegal moves return the gate's reason. The permanence language is consistent with destructiveHint=false because no fact is deleted, only superseded.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and action routing are front-loaded, which is good, but roughly half the text is server-wide permanence and secret-redaction boilerplate only loosely tied to moving a decision, and the 65536-byte limit adds length of marginal relevance. The credential/personal-data warnings are valuable but repeated in substance across two long passages.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description covers the reply behavior (attribution stated in the response, replaced values reported back, gate reason on refusal) along with preconditions, refusals, and size limits. For a five-parameter mutation with no output schema, nothing an agent needs to call it correctly appears to be missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning on top: it clarifies the conditional coupling of `by` to supersede only, the note requirement for accept/reject, the reason requirement for supersede, and the consequence of omitting them (refusal with the gate's reason). It also explains why no `project` parameter exists, which is a semantic point the schema alone cannot convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource ('Move an existing decision to a new state') and then enumerates the three legal transitions (accept, reject, supersede) with their distinct requirements. It is clearly a state-change operation on a decision, distinguishable from creating one, and an agent knows exactly what it would do without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use and when-not rules are given per action: accept/reject require a note and refuse `by`, supersede requires `by` plus a reason, and `by` applies ONLY to supersede. It also states the precondition that a `project` argument must not be supplied because the id alone resolves the project, and that accept is refused when the `agent-accepts` switch is off.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.